Codebase for reproducing the experiments of the semantic uncertainty paper (short-phrase and sentence-length experiments).

Source code of our paper MIND, ACL 2024 Long Paper

Curated tutorials and resources for Large Language Models, Text2SQL, Text2DSL、Text2API、Text2Vis and more.

A repository that contains models, datasets, and fine-tuning techniques for DB-GPT, with the purpose of enhancing model performance in Text-to-SQL

华南理工大学硕博士学位论文模板(LaTeX)。Latex templates for the thesis of South China University of Technology

Implementation of "RAT: Retrieval Augmented Thoughts Elicit Context-Aware Reasoning in Long-Horizon Generation".

Parameter-Efficient Sparsity Crafting From Dense to Mixture-of-Experts for Instruction Tuning on General Tasks

Source code of DRAGIN, ACL 2024 main conference Long Paper

主要记录大语言大模型（LLMs） 算法（应用）工程师相关的知识及面试题

Unsupervised Information Refinement Training of Large Language Models for Retrieval-Augmented Generation

算法竞赛模板库 by 灵茶山艾府 💭💡🎈

Unified Efficient Fine-Tuning of 100+ LLMs & VLMs (ACL 2024)

百度NLP：分词，词性标注，命名实体识别，词重要性

Retrieval and Retrieval-augmented LLMs

Split text into semantic chunks, up to a desired chunk size. Supports calculating length by characters and tokens, and is callable from Rust and Python.

深度学习面试宝典（含数学、机器学习、深度学习、计算机视觉、自然语言处理和SLAM等方向）

A modular graph-based Retrieval-Augmented Generation (RAG) system

Implementation of End-to-End Query Term Weighting (TW-BERT)

Topic Modelling for Humans

LangGPT: Empowering everyone to become a prompt expert!🚀 Structured Prompt，Language of GPT, 结构化提示词，结构化Prompt

DeepSpeed is a deep learning optimization library that makes distributed training and inference easy, efficient, and effective.

FastGPT is a knowledge-based platform built on the LLMs, offers a comprehensive suite of out-of-the-box capabilities such as data processing, RAG retrieval, and visual AI workflow orchestration, le…

RAGFlow is an open-source RAG (Retrieval-Augmented Generation) engine based on deep document understanding.

Efficient Retrieval Augmentation and Generation Framework

A collection of RAG systems powered by LLM.

整理目前开源的最优表格识别模型，完善前后处理，模型转换为ONNX Organize the currently open-source optimal table recognition models, improve pre-processing and post-processing, and convert the models to ONNX.